Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53947
    Prev
    Next
    INDEX
    Explanations

    Logic problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     די
    -0.08
     billions
    -0.08
     ||
    -0.08
    >>↵
    -0.08
     increasingly
    -0.08
     Millionen
    -0.07
     millions
    -0.07
    .mkdirs
    -0.07
    ディ
    -0.07
     effectiveness
    -0.07
    POSITIVE LOGITS
     clue
    0.11
     clues
    0.11
     unidentified
    0.09
     spies
    0.09
     spouses
    0.09
    .named
    0.09
     spouse
    0.09
    谁
    0.09
     namen
    0.09
     Outs
    0.09
    Activations Density 0.042%

    No Known Activations